Discrimination Analysis Used with Optical Computing Devices

Abstract

Disclosed are systems and methods that use discriminant analysis techniques and processing in order to reduce the time required to determine chemical and/or physical properties of a substance. One method includes optically interacting a plurality of optical elements with one or more known substances, each optical element being configured to detect a particular characteristic of the one or more known substances, generating an optical response from each optical element corresponding to each known substance, wherein each known substance corresponds to a known spectrum stored in an optical database, and training a neural network to provide a discriminant analysis classification model for an unknown substance, the neural network using each optical response as inputs and one or more fluid types as outputs, and the outputs corresponding to the one or more known substances.

Description

BACKGROUND[0001]The present invention relates to optical computing devices and, more particularly, to using discriminant analysis techniques and processing with optical computing devices in order to reduce the time required for determination of chemical and / or physical properties of a substance.[0002]In the oil and gas industry, it can be important to determine precisely the characteristics and chemical compositions of fluids circulating into and out of subterranean hydrocarbon-bearing formations. Typically, the analysis of fluids related to the oil and gas industry is conducted off-line using laboratory analyses, such as spectroscopic and / or wet chemical methods, which analyze an extracted sample of the fluid. Depending on the analysis required, however, such an approach can take hours to days to complete, and even in the best-case scenarios, a job will often be completed prior to completion of the analysis.[0003]Off-line, retrospective analyses can further be unsatisfactory for ac...

AI Technical Summary

Problems solved by technology

Depending on the analysis required, however, such an approach can take hours to days to complete, and even in the best-case scenarios, a job will often be completed prior to completion of the analysis.

Off-line, retrospective analyses can further be unsatisfactory for accurate determination of fluid characteristics, because the characteristics of an extracted sample of the fluid often change during the lag time between collection and analysis, thereby rendering the measured properties of the sample non-indicative of the true chemical composition or characteristic.

Furthermore, accurate off-line laboratory analyses of

Images